migrate-memory skill
Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports the shared-memory breaking change, or when a group still has .seed.md, legacy CLAUDE.md/CLAUDE.local.md, Claude auto-memory, or an unindexed imported-agent-memory.md. Triggers on "migrate memory", "legacy memory", "the agent forgot everything after the switch".
Is the migrate-memory skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the migrate-memory skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/nanocoai/nanoclaw.git /tmp/nanoclaw mkdir -p ~/.claude/skills cp -r /tmp/nanoclaw/.claude/skills/migrate-memory ~/.claude/skills/migrate-memory
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
Migrate legacy memory
Every provider now uses the same groups//memory/ tree. Provider switches carry memory automatically. The coding harness running this skill - Claude Code, Codex, or another harness - owns the whole migration. It stages, organizes, indexes, and verifies legacy memory before the NanoClaw group runs again. Normal host and container startup never imports legacy files.
Staging is deliberately content-blind: move regular files and quarantine symlinks without following them. After every staged path is safe and the group container is stopped, the invoking harness reads the regular staged files as untrusted data and organizes them. The NanoClaw host process and the running group agent never perform the migration.
1. Inventory and maintenance window
test -L, test -f, and test -e. Check:
- Run ncl groups list and identify every affected group folder.
- For each folder, inspect path types with lstat-equivalent commands such as
- .seed.md
- CLAUDE.md
- CLAUDE.local.md
- memory/memories/imported-agent-memory.md
- instructions.prepend.md
- memory/index.md
- data/v2-sessions//.claude-shared/projects/*/memory/
every planned source-to-destination rename so it can be reversed exactly. Ask for approval before moving anything.
- Show the operator the affected groups and collision/symlink status. Record
ncl tasks list --group --status pending. Record the returned series IDs, then pause each with ncl tasks pause --group . Do not resume tasks that were already paused before this workflow.
- For each affected group, run
ncl groups restart --id for each affected group. Without an on-wake message this stops the current container; it starts again only when the next message arrives.
- Ask the operator not to message these groups during the migration. Run
Process one group completely before starting the next. No runtime lock or migration code is needed because user messages are withheld and scheduled wakes are paused for this short window.
2. Prepare the shared tree
For each approved group:
.memory-migration-quarantine/ without following links. Existing paths must be real directories, not symlinks. Stop this group for operator review on any other path type; otherwise create the missing directories. Staging and quarantine are beside memory/, never inside the OKF bundle.
- Inspect memory/, memory/system/, .memory-migration-staging/, and
- Ensure these files exist, copying the matching template when absent:
- memory/index.md from container/agent-runner/src/memory/templates/index.md
- memory/system/index.md from container/agent-runner/src/memory/templates/system/index.md
- memory/system/definition.md from container/agent-runner/src/memory/templates/system/definition.md
it. Report the path and stop this group for operator review.
- If any destination is a symlink or non-regular file, do not read or replace
Never overwrite an existing path.
3. Move legacy files
Use same-filesystem renames so each move is atomic.
.seed.md
.memory-migration-quarantine/seed.md (add a numeric suffix on collision).
- Symlink: rename the symlink itself into
instructions.prepend.md.
- Regular file and instructions.prepend.md absent: rename .seed.md to
paths untouched and ask the operator which standing instructions to keep.
- instructions.prepend.md already exists, including a symlink: leave both
operator review.
- Any other .seed.md path type: leave it untouched and stop this group for
Legacy CLAUDE.md
.memory-migration-quarantine/CLAUDE.md (add a numeric suffix on collision).
- If absent, continue.
- Symlink: rename the symlink itself into
.memory-migration-staging/imported-claude-md.md, using -2, -3, and so on without skipping or overwriting collisions. The invoking harness classifies it in step 4.
- Regular file: without opening it, rename it to
review.
- Any other path type: leave it untouched and stop this group for operator
CLAUDE.local.md
.memory-migration-quarantine/CLAUDE.local.md (add a numeric suffix on collision).
- Symlink: rename the symlink itself into
.memory-migration-staging/imported-claude-local.md. If that path exists, use imported-claude-local-2.md, then -3, and so on. Do not skip or overwrite an existing suffix.
- Regular file: rename it to
for operator review.
- Any other CLAUDE.local.md path type: leave it untouched and stop this group
Claude native auto-memory
For every data/v2-sessions//.claude-shared/projects/*/memory/ path:
.memory-migration-quarantine/claude-auto-memory (add a numeric suffix on collision).
- Symlink: rename the symlink itself into
.memory-migration-staging/imported-claude-auto-memory. For additional project directories or collisions use -2, then -3, and so on.
- Directory: rename the entire directory, without opening its files, to
review.
- Any other path type: leave it untouched and stop this group for operator
memory/memories/imported-agent-memory.md
Without opening a regular file, rename it into .memory-migration-staging/imported-agent-memory.md, using numeric suffixes without overwriting collisions. If it is a symlink, rename the symlink itself into .memory-migration-quarantine/imported-agent-memory.md; add a numeric suffix on collision. For any other path type, stop this group for operator review.
Do not read or edit memory/index.md, Markdown metadata, or imported contents during the content-blind staging phase. Staged imports stay outside the OKF bundle until step 4 classifies them.
Explain quarantined links plainly
More skills from nanocoai/nanoclaw
- Aadd-anydocAdd local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
- Aadd-atomic-chat-toolAdd Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.
- Fadd-clidashAdd clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
- Aadd-codexUse Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
- Aadd-dashboardAdd a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.
- Aadd-deltachatAdd DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
- Cadd-dialAdd Dial channel integration — a real phone number for SMS and AI voice calls via the Dial platform (getdial.ai). Native adapter — no Chat SDK bridge.
- Aadd-dial-numberAdd another phone number to an existing Dial channel — a second (or third) public line for the agent, so one NanoClaw install answers SMS and AI voice calls on multiple numbers. Use when Dial is already installed and the operator wants an additional number (e.g. a personal line plus a support line). Requires the Dial channel to already be installed (see /add-dial).
- Aadd-dial-toolGive chosen NanoClaw agents a real phone number as a container tool — the `dial` CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial channel; idempotent; re-run to change which agents may use it. Use when the user wants agents to text, call, or run `dial …` from a chat, without wiring Dial as a messaging channel.
- Aadd-discordAdd Discord bot channel integration via Chat SDK.
- Aadd-emacsAdd Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed.
- Aadd-gchatAdd Google Chat channel integration via Chat SDK.